Plugins

Install suites from any Claude Code, Codex, Cursor, Kimi or agent-plugins.org git marketplace repo — skills, MCP servers, hooks and slash commands are injected into DSH sessions at runtime, with a market page in the Web GUI.

Modifies DSH plugin code at runtime, with ordered patches, inspection, and hot reload.

Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.

Finds potential UX issues in your project: automatically reviews React/TypeScript code, pinpoints each problem, and gives concrete suggestions.

Local meeting transcription with microphone and system audio recording, speaker labels, and transcript export for DeepSeek Harness on Apple Silicon macOS.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

Three Zhihu tools for DSH — in-site search, Zhihu's global web index with domain and date filters, and Zhida answers — with a native settings card and source-cited results.

Multi-user login gateway for the DSH web UI: the first visit creates the admin account, admins add and manage users in the GUI settings panel, ordinary users see only their own conversations, and unauthenticated visitors are redirected to /login.

StrataGate gives DeepSeek Harness evolving, local-first long-term memory for user preferences, project decisions, conversations, and tool results across sessions; it layers history with user-tunable time decay, reinforces memories through real answer use, shows workspace-aware usage counts, and keeps recalled evidence traceable to its original messages.

Lets one session read, write and run bash across several folders, not just the primary root — additional roots are registered from a sidebar Folders panel or the /workspace-folders command (inherit/read-only/read-write) and share the primary root's file-fence + OS-sandbox authorization; adds no new tools.

Directed fuzzing driven by an LLM agent: from a target repository and a bug (CVE description, patch, crash trace, or file:line), it runs a PLAN, IMPLEMENT, EXECUTE, REFLECT loop in which the model writes Python input generators, until an input triggers the campaign's stderr-pattern oracle or the campaign stops.

Anatomy panel for the Agent-Body organs: serves a live vitals dashboard at /anatomy inside the harness itself - organs, heartbeat, healing ledger, self-training counters and the real pulse stream - read straight from the runtime files rather than retyped. Host-only, no client bundle and no build step.

Zero-residence context engine: large tool payloads are evicted out of the live context into a queryable store and only deterministic pointers are left behind, so per-turn prompt tokens stop growing with the transcript. Any masked content is reconstructed verbatim from the session log on demand, by tool-call id or session seq.

The organ kernel of Agent-Body: plugins organized as one body. Each command is turned into a nerve impulse that deterministically innervates the organ which should handle it and names the capability to use; a heartbeat with a variable interval (faster on alerts, slower when idle) pumps operator directives, proprioception and homeostasis warnings system-wide; reflex arcs fire with zero model calls; failures go through deterministic attribution (missing tool / arguments / permission / timeout / network), a prescription, and a re-check loop, with argument errors never auto-retried. A missing organ is compensated by the one with the highest capability overlap, and tool schemas are gated by the current intent (84.7% measured reduction, reproducible in-repo). This entry is the kernel plugin package inside the agent-body repository.

The memory organ of Agent-Body: after 2 minutes of silence it enters light sleep and after 5 minutes deep sleep, where deterministic rules distil real experience into memory cards (pitfalls, playbooks, hotspots, unresolved issues, facts). Incoming commands recall related cards by keyword and inject them into context; cards unused for long decay on a half-life and are archived rather than deleted. It also de-noises body-wide homeostasis warnings: repeats inside a window are counted instead of re-printed, and a warning that keeps recurring without ever healing converges into a known steady-state offset and goes quiet. Consolidation and recall make no model calls.

AI 原生智能爬虫与 JavaScript 逆向工程平台，基于 DSH、Patchright/CDP 与独立语义运行时，从浏览器证据恢复参数生成逻辑并交付可验证 Solver。

Galgame generator: give it a script document plus character/background/BGM/animation assets in the workspace (img_human/, img_bg/, audio/, img_cg/) and it builds a playable visual-novel web page with configurable save slots (`[存档 N]`, default 9), speaker-following sprites with multi-pose variant switching (`[表情]`), opening/ending/CG animations (`[op]`/`[ed]`/`[cg]`), BGM play/stop/volume control, and if-line branching.

Terminal-style input history for the web composer: edge-first arrow-key recall with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, and sliding-context awareness; 0.5.0 adds a smart input layer — cross-session snippets (/save, /load), prompt templates with variables, reuse insights, and compaction-summary highlighting.

Adds image_generate and image_library tools that pick reference images from four local libraries (characters, outfits, scenes, props), expand situation, expression, pose, shot and light keyword presets into the prompt, and call the 65535 async task API or any OpenAI-compatible images API, showing the result in the conversation; a settings page manages the libraries and turns an uploaded image or a text description into a three-view reference sheet. With dsh-daily-schedule installed, an image without a specified outfit uses what the character is wearing in the current schedule entry.

Render Mermaid code fences as SVG diagrams with streaming support, diagram/code switching, fullscreen zoom and pan, SVG export, and a bundled same-origin runtime.

Modifies DSH plugin code at runtime, with ordered patches, inspection, and hot reload.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

WeChat (personal WeChat, iLink Bot API) channel: chat with your DSH agent from WeChat, with images, files and voice-note transcription. One WeChat conversation can hold several DSH Sessions (/new, /list, /use) and every option is editable from the settings page. Also published to npm as dsh-plugin-weixin.